A Learning Approach for Adaptive Image Segmentation

Martin, Vincent; Thonnat, Monique; Maillot, Nicolas

doi:10.1109/icvs.2006.4

Cited by 17 publications

(7 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This family of methods is called supervised segmentation methods. The most frequent use of examples (or ground truth in the field of remote sensing) is to perform an optimization to find the best segmentation parameters (Bhanu et al, 1995;Pignalberi et al, 2003;Song and Ciesielski, 2003;Martin and Maillot, 2006;Feitosa et al, 2006). This kind of methods involves a common segmentation algorithm which can be tuned by a set of parameters.…”

Section: Supervised Segmentationmentioning

confidence: 98%

Supervised image segmentation using watershed transform, fuzzy classification and evolutionary computation

Derivaux¹,

Forestier²,

Wemmert³

et al. 2010

Pattern Recognition Letters

View full text Add to dashboard Cite

International audienceAutomatic image interpretation is often achieved by first performing a segmentation of the image (i.e., gathering neighbouring pixels into homogeneous regions) and then applying a supervised region-based classification. In such a process, the quality of the segmentation step is of great importance in the final classified result. Nevertheless, whereas the classification step takes advantage from some prior knowledge such as learning sample pixels, the segmentation step rarely does. In this paper, we propose to involve such samples through machine learning procedures to improve the segmentation process. More precisely, we consider the watershed transform segmentation algorithm, and rely on both a fuzzy supervised classification procedure and a genetic algorithm in order to respectively build the elevation map used in the watershed paradigm and tune segmentation parameters. We also propose new criteria for segmentation evaluation based on learning samples. We have evaluated our method on remotely sensed images. The results assert the relevance of machine learning as a way to introduce knowledge within the watershed segmentation process

show abstract

Section: Supervised Segmentationmentioning

confidence: 98%

Supervised image segmentation using watershed transform, fuzzy classification and evolutionary computation

Derivaux¹,

Forestier²,

Wemmert³

et al. 2010

Pattern Recognition Letters

View full text Add to dashboard Cite

show abstract

“…The principal limitation of the method is that the segmentation evaluation metric has been defined for the specific task of vesselneurite segmentation and makes the system unsuitable for other applications. In [12], Martin et al tackle the problem of optimal parameter extraction for several state-of-the-art region-based segmentation algorithms. They use a direct search method, the simplex algorithm, to maximize an objective function based on a spatial accuracy evaluation metric.…”

Section: Related Workmentioning

confidence: 99%

“…But these techniques do not accomplish any learning from experience nor adaptation independently of detailed knowledge pertinent to segmentation algorithm. To overcome this limitation, optimization and learning-based frameworks have been proposed to automatically select the segmentation algorithm [22,12] and/or tune the algorithm parameters [3,23,9,15,1,12]. The proposed optimization procedure can overcome such limitations by decomposing the problem into three fundamental and independent components: a segmentation algorithm with its free-parameters to tune, a segmentation evaluation metric and a global optimization algorithm.…”

Section: Related Workmentioning

confidence: 99%

A Cognitive Vision Approach for Image Segmentation Thresholding Images of Historical Documents with Back-to-Front Interference

Filho

Mello

Andrade

et al. 2007

19th IEEE International Conference on Tools With Artificial Intelligence(ICTAI 2007)

View full text Add to dashboard Cite

In many vision problems, the performance of the segmentation step is highly dependent on the algorithm selection and its parametrization. These tasks are tricky and time-consumming. In this paper, we present an approach to perform task-oriented segmentation based on segmentation algorithm parameter tuning and learning techniques. We propose a scheme that, for each segmentation algorithm to test, first extracts optimal parameters and second learns the region labeling according to the segmentation task. This supervised approach uses two kinds of groundtruth data: manual region-based segmentations and semantic region labels. The first step consists in extracting optimal segmentation algorithm parameters by using a closed-loop optimization procedure, an evaluation metric and groundtruth (manual region segmentations). During the second step, region classifiers are trained based on ground-truth annotations (semantic region labels) to allow segmentation labeling. This knowledge (i.e. optimal parameters and learned region classifiers) is then used to produce an optimized class-based segmentation of new images. Our main contribution is to propose a methodology to easily set up the segmentation task in vision systems. Our method only requires the user to provide segmentation algorithms and labeled ground-truths. The experiment on a biological application shows that our optimization scheme is reliable for different state-of-the-art segmentation algorithms. Evaluation of results also demonstrates that the optimized classbased segmentation achieves a better level of accuracy than the non-optimized class-based segmentation approach.

show abstract

“…The main objective of segmentation is separating background and foreground to extract the regions of interest in the image. Despite the variety of existing methods for image segmentation with promising performance, it is still not proven that these methods can be used in diverse applications [11]. In these methods, the key parameters are manually tuned by system designers using trial and errors approaches, and the parameters cannot be adapted to environmental changes.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Image Thresholding of Yellow Peppers for a Harvesting Robot

2018

View full text Add to dashboard Cite

Abstract:The presented work is part of the H2020 project SWEEPER with the overall goal to develop a sweet pepper harvesting robot for use in greenhouses. As part of the solution, visual servoing is used to direct the manipulator towards the fruit. This requires accurate and stable fruit detection based on video images. To segment an image into background and foreground, thresholding techniques are commonly used. The varying illumination conditions in the unstructured greenhouse environment often cause shadows and overexposure. Furthermore, the color of the fruits to be harvested varies over the season. All this makes it sub-optimal to use fixed pre-selected thresholds. In this paper we suggest an adaptive image-dependent thresholding method. A variant of reinforcement learning (RL) is used with a reward function that computes the similarity between the segmented image and the labeled image to give feedback for action selection. The RL-based approach requires less computational resources than exhaustive search, which is used as a benchmark, and results in higher performance compared to a Lipschitzian based optimization approach. The proposed method also requires fewer labeled images compared to other methods. Several exploration-exploitation strategies are compared, and the results indicate that the Decaying Epsilon-Greedy algorithm gives highest performance for this task. The highest performance with the Epsilon-Greedy algorithm ( = 0.7) reached 87% of the performance achieved by exhaustive search, with 50% fewer iterations than the benchmark. The performance increased to 91.5% using Decaying Epsilon-Greedy algorithm, with 73% less number of iterations than the benchmark.

show abstract

A Learning Approach for Adaptive Image Segmentation

Cited by 17 publications

References 37 publications

Supervised image segmentation using watershed transform, fuzzy classification and evolutionary computation

Supervised image segmentation using watershed transform, fuzzy classification and evolutionary computation

A Cognitive Vision Approach for Image Segmentation Thresholding Images of Historical Documents with Back-to-Front Interference

Adaptive Image Thresholding of Yellow Peppers for a Harvesting Robot

Contact Info

Product

Resources

About